Abstractive text summarization based on neural fusion

Abstractive text summarization, in comparison to extractive text summarization, offers the potential to generate more accurate summaries. In our work, we present a stage-wise abstractive text summarization model that incorporates Elementary Discourse Unit (EDU) segmentation, EDU selection, and EDU fusion. We first segment the articles into a fine-grained form, EDUs, and build a Rhetorical Structure Theory (RST) tree for each article in order to represent the dependencies among EDUs; those EDUs are encoded in Graph Attention Networks (GATs); those with higher importance will be selected as candidates to be fused and the fusing stage is done by Bidirectional and Auto-Regressive Transformers (BART) model which merges the selected EDUs into summaries. A Greedy Method is leveraged to greedily select those EDUs whose combinations can maximize the ROUGE scores. Our model outperforms the baseline of BART (large) on the CNN/Daily Mail dataset, showing its effectiveness in abstractive text summarization.

Authors

• Zhu, Wenzhao
• University of Lethbride. Faculty of Arts and Science

• Abstractive text summarization
• Elementary discourse unit
• Rhetorical structure theory
• Neural networks
• Neural fusion

Identifier

hdl:10133/6669

OAI identifier oai:identifier

oai:opus.uleth.ca:10133/6669